Bearing Fault Diagnosis Method Based On Convolutional Neural Network And Ensemble Learning

Intelligent fault diagnosis of bearings is an essential issue in the field of health management and the prediction of rotating machinery systems.The traditional bearing intelligent diagnosis algorithms based on the combination of feature extraction and classification for signal processing require high expert experience,which are time-consuming and lack universality.Compared with traditional methods,the convolutional neural network(CNN)can extract features automatically from the original vibration time-domain signal without any preprocessing.The accuracy of intelligent fault diagnosis can be improved by utilizing the multi-layer nonlinear mapping capability of deep convolutional neural networks.Intelligent diagnosis of bearing faults is realized by end-to-end method.The main research contents of this paper are as follows:(1)In order to realize the "end-to-end" intelligent diagnosis of bearing faults and improve the accuracy of fault diagnosis,the third chapter of this paper is based on the deep convolutional neural network technology and combined with the characteristics of one-dimensional time-domain signals.the convolutional neural network with wide convolution kernels(WKCNN)model and its construction algorithm are proposed.The model performs well in the aspects of fault diagnosis accuracy,timeliness,antinoise interference and variable load transfer without any pre-processing.(2)In order to solve the problem that the industrial field can only collect the small sample label data,the fourth chapter of this paper is based on the idea of Stacking integrated learning,the multiple single-layer convolutional neural network as a basic learning device,the fully connected neural network as a meta-learning device,The SSCNN-X(X Single Layer Convolutional Neural Networks)model is proposed.The experimental results show that the diagnostic accuracy of this model is 5% higher than that of WKCNN and 11% higher than that of its base learner in the environment of small sample training set,which proves the effectiveness of this fusion method.(3)Based on the above theoretical basis and algorithm,the fifth chapter of this paper designs a set of intelligent diagnosis platform for bearing faults based on Spring Boot + VUE front-end separation technology and combined with Python machine learning framework,which realizes the functions of model training,model saving and real-time diagnosis of bearing faults in the system.